Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes well beyond the sparse annotations. It discloses non-custodial transaction signing, the exact two-phase build/broadcast flow, fee mechanics, the 90-day jurisdiction memory, geo-denial policy, idempotent replay semantics, and verification response content. This aligns with destructiveHint=true and provides materially useful operational context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but it is dense and sectioned by bolded parameter names, making it scannable. The first line delivers the core purpose. Some idempotency nuance is verbose, but it is justified by the risk of duplicate on-chain orders.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter, non-custodial, multi-phase perp tool, the description is nearly complete. It covers required fields, return behavior, geo constraints, idempotency, verification, and when to trust confirmation. Minor gaps include the unidirectional meaning of allow_unverified and pay_in_crank, and there is no explicit mention of the output schema's detailed shape, though the description includes the key verification block fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Given 0% schema description coverage, the prose does heavy lifting: market example, notional size_usd, leverage limits, jurisdiction syntax/expiry, idempotency_key replay rules, signed_transaction/verify phase behavior, and TP/SL informational role are all explained. Some parameters like allow_unverified, pay_in_crank, caller_id, and ip remain undocumented, so it is not perfect, but the critical execution parameters are very well covered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific operation: open a leveraged LONG perp position on Drift, returns an unsigned base64 transaction, and gives entry/liquidation/margin context. It clearly differentiates from sibling perp_open_short and other perp order tools by direction and scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Strong operational guidance: TP/SL are informational and must be placed after opening, jurisdiction is mandatory and geo-gated, idempotency key must be reused across build/completion, and gate decisions on verification.confirmed rather than tx_signature. It lacks an explicit paragraph naming alternatives like perp_open_short or place_perp_order, but the LONG framing makes the primary use case unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.